GPT-5.6 Cyber
gpt-5.6-cyberPricing
List prices at OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $12.50 | $75.00 | |
| Cached input 90% off input | $1.25 | 90% off input | |
| Cache write, 5 minutes | $15.63 | ||
| Prompts over 272K tokens | $25.00 | $112.50 |
What it costs a month
At OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$8,363
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$6,000
- Coding agent1,000 requests a day, 40K in / 2K out, cached$10,050
- Overnight batch20,000 requests a day, 4K in / 0.4K out$48,000
Where to run it
2 hosts serve GPT-5.6 Cyber. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
OpenAILab API gpt-5.6-cyber | $12.50 / $75.00 | gpt-5.6-cyber | |
| $12.50 / $75.00 | global.openai.gpt-5.6-cyber |
Show 3 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| Mantle openai.gpt-5.6-cyber | $13.75 / $82.50 +10% vs headline | openai.gpt-5.6-cyber | |||||
| us us.openai.gpt-5.6-cyber | $13.75 / $82.50 +10% vs headline | us.openai.gpt-5.6-cyber | |||||
| us-gov-east-1 · Mantle openai.gpt-5.6-cyber | $16.88 / $101.25 +35% vs headline | openai.gpt-5.6-cyber | |||||
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- ImagesTextPDFs
- Produces
- Text
- Features
- Computer useParallel tool callsPDF inputPrompt cachingBuilt-in web search
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than OpenAI.
Smaller OpenAI models
- 43% less
- 83% less
- 86% less
Other frontier labs
- 43% less
- 86% less
- 89% less
- 72% less
Open-weight picks
- 86% less
- 92% less
- 94% less
- 98% less
Model line
Newer and older versions, at each lab's own price.
- UndatedGPT-6 CyberLatest$20.00 / $100.00
- UndatedGPT-5.6 CyberThis page$12.50 / $75.00
- UndatedGPT-5.5 Cyber$12.50 / $75.00
Call it
Using OpenAI's API.
from openai import OpenAI
client = OpenAI() # reads OPENAI_API_KEY
response = client.responses.create(model="gpt-5.6-cyber", input="Hello")
print(response.output_text)curl https://api.openai.com/v1/responses \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-5.6-cyber", "input": "Hello"}'from litellm import completion
response = completion(
model="openai/gpt-5.6-cyber",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-5.6 Cyber cost?
On OpenAI, GPT-5.6 Cyber costs $12.50 per million input tokens and $75.00 per million output tokens. Cached input costs $1.25 per million tokens.
Which APIs offer GPT-5.6 Cyber?
GPT-5.6 Cyber runs on 2 APIs: OpenAI and Amazon Bedrock.
What is GPT-5.6 Cyber's context window?
272K tokens, with up to 128K tokens in one reply.
Is GPT-5.6 Cyber being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of GPT-5.6 Cyber?
Yes. GPT-6 Cyber is the newest model in this line.
What are cheaper alternatives to GPT-5.6 Cyber?
Models that cost less and keep most of what it can do: GPT-6.2 Astra on OpenAI (43% less), Claude Fable 5.2 on Anthropic (43% less), Gemini 4 Carbon on Google AI Studio (86% less) and Kimi K3.1 Pro on Databricks (86% less). Savings are on a mix of 3 input tokens to 1 output token.
What is GPT-5.6 Cyber's API model id?
Use gpt-5.6-cyber with OpenAI. Other hosts use their own ids: global.openai.gpt-5.6-cyber on Amazon Bedrock.
Sources
Raw catalog entry for gpt-5.6-cyber on OpenAI
{
"cache_creation_input_token_cost": 0.000015625,
"cache_creation_input_token_cost_above_12hr": 0.00003125,
"cache_creation_input_token_cost_above_272k_tokens": 0.00003125,
"cache_read_input_token_cost": 0.00000125,
"cache_read_input_token_cost_above_272k_tokens": 0.0000025,
"input_cost_per_token": 0.0000125,
"input_cost_per_token_above_272k_tokens": 0.000025,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 0.000075,
"fedramp_uplift_multiplier": 1.1,
"output_cost_per_token_above_272k_tokens": 0.0001125,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true,
"source": "https://developers.openai.com/api/docs/pricing",
"supports_computer_use": true,
"supports_parallel_function_calling": true
}